Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

/pdf/deep-residual-learning-for-image-recognition-b75jg61qrq.pdf

Deep Residual Learning for Image Recognition

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. 
The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Capturing the motion of two hands interacting with an object is a very challenging task due to the large number of degrees of freedom, self-occlusions, and similarity between the fingers, even in the case of multiple cameras observing the scene. In this paper we propose to use discriminatively learned salient points on the fingers and to estimate the finger-salient point associations simultaneously with the estimation of the hand pose. We introduce a differentiable objective function that also takes edges, optical flow and collisions into account. Our qualitative and quantitative evaluations show that the proposed approach achieves very accurate results for several challenging sequences containing hands and objects in action.

/pdf/motion-capture-of-hands-in-action-using-discriminative-x9x41byer2.pdf

Motion capture of hands in action using discriminative salient points

We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled feature patches and their corresponding votes in a spatio-temporal-action Hough space. The leaves of the trees form a discriminative multi-class codebook that share features between the action classes and vote for action centers in a probabilistic manner. Using low-level features such as gradients and optical flow, we demonstrate that Hough-voting can achieve state-of-the-art performance on several datasets covering a wide range of action-recognition scenarios.

/pdf/a-hough-transform-based-voting-framework-for-action-5cumv6lky9.pdf

A Hough transform-based voting framework for action recognition

We present a learned image compression system based on GANs, operating at extremely low bitrates. Our proposed framework combines an encoder, decoder/generator and a multi-scale discriminator, which we train jointly for a generative learned compression objective. The model synthesizes details it cannot afford to store, obtaining visually pleasing results at bitrates where previous methods fail and show strong artifacts. Furthermore, if a semantic label map of the original image is available, our method can fully synthesize unimportant regions in the decoded image such as streets and trees from the label map, proportionally reducing the storage cost. A user study confirms that for low bitrates, our approach is preferred to state-of-the-art methods, even when they use more than double the bits.

/pdf/generative-adversarial-networks-for-extreme-learned-image-56tclqa517.pdf

Generative Adversarial Networks for Extreme Learned Image Compression

This paper reviews the 2nd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with focus on proposed solutions and results. The challenge had 4 tracks. Track 1 employed the standard bicubic downscaling setup, while Tracks 2, 3 and 4 had realistic unknown downgrading operators simulating camera image acquisition pipeline. The operators were learnable through provided pairs of low and high resolution train images. The tracks had 145, 114, 101, and 113 registered participants, resp., and 31 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

/pdf/ntire-2018-challenge-on-single-image-super-resolution-2vtucnano0.pdf

NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results

Traffic sign recognition has been a recurring application domain for visual objects detection. The public datasets have only recently reached large enough size and variety to enable proper empirical studies. We revisit the topic by showing how modern methods perform on two large detection and classification datasets (thousand of images, tens of categories) captured in Belgium and Germany. We show that, without any application specific modification, existing methods for pedestrian detection, and for digit and face classification; can reach performances in the range of 95% ~ 99% of the perfect solution. We show detailed experiments and discuss the trade-off of different options. Our top performing methods use modern variants of HOG features for detection, and sparse representations for classification.

Luc Van Gool

Papers

Motion capture of hands in action using discriminative salient points

A Hough transform-based voting framework for action recognition

Generative Adversarial Networks for Extreme Learned Image Compression

NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results

Traffic sign recognition — How far are we from the solution?